notesum.ai

Published at November 27

Neutralizing Backdoors through Information Conflicts for Large Language Models

cs.CL

Released Date: November 27, 2024

Authors: Chen Chen1, Yuchen Sun2, Xueluan Gong1, Jiaxin Gao2, Kwok-Yan Lam1

Aff.: 1Nanyang Technological University, Singapore; 2Wuhan University, China

Arxiv: http://arxiv.org/abs/2411.18280v1